skillZs
★ LIVE SKILL TAGS ★
>>> LIVE SKILLS INDEX <<<
* OPEN SOURCE *
NO LOGIN, NO TRACKING
※ REAL INSTALL DATA ※
← back to all skills
hjewkes/agent-skills56 installs

code-review

Unified code review system — dispatches the right review agents for the situation. Use when reviewing code for quality, bugs, compliance, or before merging.

How do I install this agent skill?

npx skills add https://github.com/hjewkes/agent-skills --skill code-review
view source ↗

Is this agent skill safe to install?

  • Gen Agent Trust Hubpass

    This skill provides a structured code review system that utilizes multiple specialized agents to analyze code changes. The primary security consideration is the risk of indirect prompt injection, as the skill processes untrusted git diffs and commit logs which could contain malicious instructions designed to manipulate the review process. It also relies on local command execution (git) and mentions browser automation tools (Playwright) for audits.

  • Socketpass

    No alerts

  • Snykpass

    Risk: LOW · No issues

  • Runlayerwarn

    10/11 files flagged

What does this agent skill do?

Code Review

Dispatch specialized review agents matched to the situation. Choose a mode or let context guide you.

Review Modes

Quick Review

When: Ad-hoc checks, quick sanity check, low-noise feedback Dispatch: quick-reviewer agent (confidence scoring, reports only >= 80) Output: High-confidence issues grouped by severity (Critical 90-100, Important 80-89)

Deep Review

When: After completing a feature, before merge, in plan-execution review loop Dispatch: deep-reviewer agent (full checklist with template placeholders) Placeholders: {WHAT_WAS_IMPLEMENTED}, {PLAN_OR_REQUIREMENTS}, {BASE_SHA}, {HEAD_SHA}, {DESCRIPTION} Output: Strengths, Issues (Critical/Important/Minor), Recommendations, Merge verdict

Specialist Review

When: Targeted analysis of a specific quality dimension Dispatch: One or more specialist agents:

AgentFocus
comment-analyzerComment accuracy, documentation quality, comment rot
test-analyzerTest coverage quality, behavioral coverage gaps, test resilience
silent-failure-hunterError handling, silent failures, catch block specificity
type-design-analyzerType invariants, encapsulation, type usefulness

Comprehensive Review

When: Before merging to main, finishing a development branch Dispatch: 4-pass structure (TDD compliance, diff-only quality, contextual quality, browser audit). See references/comprehensive-review-procedure.md for pass details and ordering.

How to Request

  1. Gather git context using scripts/review-prep (auto-detects base branch, outputs BASE_SHA, HEAD_SHA, diff stats, changed files, commit log). Use --json for structured output.
  2. Read the reference file for your chosen agent(s)
  3. Spawn general-purpose Task agent with the prompt + review-prep output
  4. Act on feedback: fix Critical immediately, fix Important before proceeding

Workflow Integration

WorkflowReview Mode
plan-execution (per-task)Deep Review
plan-execution (batch)Deep Review
Before merge to mainComprehensive Review
Ad-hoc / when stuckQuick Review
Specific concernSpecialist Review
GitHub PR review + postinggithub-pr skill (automated PR review orchestrator)

Simplification Mode

After review, optionally dispatch a simplification pass to improve clarity, consistency, and maintainability without changing functionality. Read references/simplifier.md for the full agent prompt, then spawn a general-purpose Task agent with that prompt targeting the reviewed files.

Handling Feedback

When receiving code review feedback (from humans or other agents), follow the structured 6-step response pattern: READ, UNDERSTAND, VERIFY, EVALUATE, RESPOND, IMPLEMENT. No performative agreement — verify before implementing, push back with technical reasoning when warranted. See references/handling-feedback.md for the full pattern, push-back criteria, YAGNI checks, and source-specific handling.

Red Flags

  • Skipping review because "it's simple"
  • Ignoring Critical issues
  • Proceeding with unfixed Important issues
  • Running Comprehensive passes all sequentially (1+2 are independent, parallelize)
  • Not deduplicating between Pass 2 and Pass 3 in Comprehensive mode

Reference Files

AgentReference
deep-reviewerreferences/deep-reviewer.md
quick-reviewerreferences/quick-reviewer.md
comment-analyzerreferences/comment-analyzer.md
test-analyzerreferences/test-analyzer.md
silent-failure-hunterreferences/silent-failure-hunter.md
type-design-analyzerreferences/type-design-analyzer.md
simplifierreferences/simplifier.md
handling-feedbackreferences/handling-feedback.md

Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.

<a href="https://skillzs.dev/skills/hjewkes/agent-skills/code-review">View code-review on skillZs</a>